© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 6585
    Prev
    Next
    INDEX
    Explanations

    verbs related to observation or actions taken by characters in a story

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    393
    +0.14
    0.6%
    1
    +0.11
    0.5%
    453
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    172
    +0.14
    0.10
    703
    +0.11
    0.09
    236
    +0.10
    0.11
    Negative Logits
    rolet
    -0.84
    hazard
    -0.74
    lean
    -0.74
    kaya
    -0.70
    Lean
    -0.69
    éļ
    -0.69
    etter
    -0.69
    Fa
    -0.69
    åij
    -0.68
    estones
    -0.67
    POSITIVE LOGITS
    soever
    1.10
     someone
    0.89
     they
    0.88
     she
    0.84
     we
    0.79
     landlords
    0.78
     anyone
    0.77
     governments
    0.76
     bubbles
    0.74
     premature
    0.73
    Activations Density 2.460%

    No Known Activations